The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they’re not affected by light conditions, can penetrate walls and other obstacles, and they’re more privacy-preserving than visual images.

[…] The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.

  • Echo Dot@feddit.uk
    cake
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    1
    ·
    53 minutes ago

    The resulting image must just basically look like a shadow, I can’t imagine that they’re going to get much internal detail with Wi-Fi considering that my router’s signal practically gets blocked by a piece of cardboard.

    This research essentially amounts to, humans can be individually identified with nothing more than low quality x-rays. Well yeah, so what, you can also use visible light and in any situation where you’re going to use Wi-Fi to detect someone, it’s got to be easier to buy a cheap CCTV camera.

    • douglasg14b@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      9 minutes ago

      Given your in-depth knowledge of Wi-Fi to consider it blocked by cardboard, I somehow doubt the rest of this comment is credible…

    • douglasg14b@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      8 minutes ago

      Everything is incremental progress in some way.

      I remember years back someone doing experiments with Wi-Fi to see if a room was occupied based on signal attenuation.

      This just looks like an extension of that.

      Not everything is a giant leap

    • StenSaksTapir@feddit.dk
      link
      fedilink
      English
      arrow-up
      16
      ·
      10 hours ago

      Well I heard about this and thought “this will be great for home automation”, but I also know that someone was equally excited about using this to rob people of basic freedoms or being a fucking creep or both.

      • Echo Dot@feddit.uk
        cake
        link
        fedilink
        English
        arrow-up
        1
        ·
        53 minutes ago

        If it’s your home why can’t you just have a camera or motion sensor. Rather than trying to adapt something that isn’t designed for the purpose.

    • gcheliotis@lemmy.world
      link
      fedilink
      English
      arrow-up
      22
      ·
      15 hours ago

      I can imagine this being initially an accidental discovery like oh every time so and so’s body interacts with the WiFi signal it’s the same pattern… until someone starts exploring this further… and then some engineer or their manager started looking for applications for this. In my experience engineering researchers especially are very good with coming up with use cases for whatever tech they’re working with, with little ethical consideration.

      • sugar_in_your_tea@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        5
        ·
        9 hours ago

        I doubt it. You’d need to be looking really closely at the waveforms to notice this, so they were likely already doing something similar, like that research that can pinpoint where people are in a house based on their WiFi. They were probably already doing something creepy before they noticed that this was more straightforward than they expected.

        • turtlesareneat@discuss.online
          link
          fedilink
          English
          arrow-up
          4
          ·
          5 hours ago

          Once you start playing with radiowaves and antenna you start noticing the intricate ways it plays with and around bags of water like bodies. I’m sure the original research on location/movement tracking was due to scientists trying not to get interference, later once they figured it out it was natural to see how much data they could get out of a radio interference profile.

          I remember the original tech was going to be marketed as a way to tell if your old person (parent etc) had fallen down and stopped moving. Not the best use case, and then the privacy implications became clear. Once that happens the race begins to exploit the tech.

          …But the eventuality here is something like a Star Trek tricorder that can take multiple vitals and detect irregularities from across the waiting room. Sensors that remember who was in a room and what settings they had. Etc. Some cool thing besides the bad stuff (microtarget those ads).

  • Sabata@ani.social
    link
    fedilink
    English
    arrow-up
    42
    ·
    20 hours ago

    Incorrect bio-signature detected, drink verification can to continue your content.

  • Seleni@lemmy.world
    link
    fedilink
    English
    arrow-up
    65
    ·
    edit-2
    1 day ago

    accurate matches up to 95.5% of the time

    and they’re more privacy-preserving than visual images

    Oh fuck all the way off.

    • D_C@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      6
      ·
      16 hours ago

      When anyone or anything says that their product works “up to x%” I always presume it doesn’t really work at all.
      Christ, 1% is included in that “up to 95.5%” vague bullshit statement.

      • novus_dervish@lemmynsfw.com
        link
        fedilink
        English
        arrow-up
        1
        ·
        14 hours ago

        I believe the reason they had to say “up to” is because the “signatute” will vary day to day ever so slightly (natural weight fluctuation), and if you gain or lose weight it can change dramatically, so the AI would have to constantly consider that and adjust it’s records.

        Honestly, unpopular opinion, but as long as it isn’t very short wavelength RF and they allow for self-hosted/open-source alternatives, I do find it a bit more privacy respecting than cameras, of course they have to say they are using the technology in public places.

        It also has it’s ways of fooling it, instead of wearing a wig and a false nose, you could wear a carbon-infused silicone fat suit to change the way you interact with RF.

  • unmagical@lemmy.ml
    link
    fedilink
    English
    arrow-up
    96
    arrow-down
    1
    ·
    1 day ago

    I’m generally pro research, but occasionally I come across a body of research and wish I could just shut down what they’re doing and rewind the clock to before that started.

    There is no benefit of this for the common person. There is no end user need or product for being able to identify individuals based on their interactions with WiFi signals. The only people that benefit from this are large corporations and governments and that’s from them turning it on you.

    Continued research will ease widespread surveillance and mass tracking. That’s not a good thing.

    • Revan343@lemmy.ca
      link
      fedilink
      English
      arrow-up
      2
      arrow-down
      1
      ·
      14 hours ago

      There is no end user need or product for being able to identify individuals based on their interactions with WiFi signals

      Cat tracker

      • unmagical@lemmy.ml
        link
        fedilink
        English
        arrow-up
        1
        ·
        11 hours ago

        Why do you need to identify specific cats over merely the presence of movement or cats in general?

        • Revan343@lemmy.ca
          link
          fedilink
          English
          arrow-up
          2
          ·
          11 hours ago

          Because I want to know which cat is getting up to shit they shouldn’t :P

    • Vinstaal0@feddit.nl
      link
      fedilink
      English
      arrow-up
      7
      arrow-down
      3
      ·
      23 hours ago

      It is cool for home automation if you can turn it into a presence detection software (do not connect your Homeassistant to the internet though)

      • unmagical@lemmy.ml
        link
        fedilink
        English
        arrow-up
        7
        ·
        15 hours ago

        If all you need is presence detection then a motion sensor would be vastly more efficient.

        If you actually need identity detection, then maybe, but you’ll still have to have a camera or detailed access logs to associate the interference signature with a known entity and at that point you may as well just put an RFID reader under the bowl you throw your keys into or use facial or gait detection.

      • unmagical@lemmy.ml
        link
        fedilink
        English
        arrow-up
        8
        ·
        15 hours ago

        Probably not.

        This kind of thing relies on the fact that the emitter and environments are static, impacting the propagation of the signals in a predictable way and that each person, having a unique physique, consistently interferes with that propagation in the same way. It’s a tool that reports “the interference in this room looks like the same interference observed in these past cases.”

        Search and rescue is a very dynamic environment, with no opportunity to establish a local baseline, and with a high likelihood that the physiological signal you are looking for has been altered (such as by broken or severed limbs).

        There are some other WiFi sniffing technologies that might be more useful for S&R such as movement detection, but I’m not sure if that will work as well when the broadcaster is outside the environment (as the more rubble between the emitter and the target the weaker your signal from reflections against the rubble).

        Don’t think of this as being able to see through walls like with a futuristic camera, think of this as AI assisted anomaly detection in signal processing (which is exactly what the researchers are doing).

      • Revan343@lemmy.ca
        link
        fedilink
        English
        arrow-up
        2
        ·
        14 hours ago

        Being able to scan and model a 3D environment using wifi? Sure. Wifi-fingerprinting the people in the scan? Why?

        • Jarix@lemmy.world
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          7 hours ago

          I mean I don’t understand this as a lay person, so if it doesn’t work then fair enough, but if wifi signals can identify human beings, and pets, when a building collapses better than other methods, or even augment the capabilities already used, then at least there is some benefit from this technique. It’s not going to disappear, Genie is out of the bottle now, so why not at least put it to a good use instead of keeping it only being abused by the billionaires and other evil entities.

          It’s too late now to stop that and I hate that they can do this.

          Please don’t mistake me trying to find a silver lining as anything other than trying to find a reason that this isn’t just another way we are fucked but the science is what it is so out it to better use. It’s an interesting capability regardless of how it can be abused, and since we aren’t going to stop using the technology we should really understand exactly how this works by using it and making it was beneficial as possible… Until we were ready to ban the tech, which I have no faith that we will ever.

          A bespoke device made to do this, not just your wifi router at home, might as well study it for good praises, or we may if only be abused with little defence against our collective abusers

  • besselj@lemmy.ca
    link
    fedilink
    English
    arrow-up
    137
    arrow-down
    1
    ·
    1 day ago

    Ironically, a tin foil hat would probably work to prevent that kind of surveillance

  • hisao@ani.social
    link
    fedilink
    English
    arrow-up
    72
    arrow-down
    1
    ·
    1 day ago

    I’ve seen some article recently that the patterns of Wi-Fi/Bluetooth (don’t remember which one) interference with brainwaves can be scanned to reconstruct brainwave signature remotely, meaning that it might be possible to scan anyone’s EEG from Wi-Fi/Bluetooth distance. And there are some AI advancements for reconstructing inner monologue from EEG. So maybe we’re not so far from actual remote mind-reading.

    • IhaveCrabs111@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      5 hours ago

      If it doesn’t get used for bad purposes it is very cool yes. So no it’s not cool at all. It’s fucked.